Search results for: interpolation accuracy

Authors: Seyed Sadegh Naseralavi, Mohsen Khatibinia

Abstract:

In structural optimizations through meta-heuristic algorithms, analyses of structures are performed for many times. For this reason, performing the analyses in a time saving way is precious. The importance of the point is more accentuated in time-history analyses which take much time. To this aim, peak picking methods also known as spectrum analyses are generally utilized. However, such methods do not have the required accuracy either done by square root of sum of squares (SRSS) or complete quadratic combination (CQC) rules. The paper presents an efficient technique for evaluating the dynamic responses during the optimization process with high speed and accuracy. In the method, first by using a static equivalent of the earthquake, an initial design is obtained. Then, the displacements in the modal coordinates are achieved. The displacements are herein called basic modal displacements (MBD). For each new design of the structure, the responses can be derived by well scaling each of the MBD along the time and amplitude and superposing them together using the corresponding modal matrices. To illustrate the efficiency of the method, an optimization problems is studied. The results show that the proposed approach is a suitable replacement for the conventional time history and spectrum analyses in such problems.

Keywords: basic modal displacements, earthquake, optimization, spectrum

Procedia PDF Downloads 361

Authors: Jay P. Sipani, Riki H. Patel, Trushit Upadhyaya

Abstract:

Today there is a demand to monitor environmental factors almost in all research institutes and industries and even for domestic uses. The analog data measurement requires manual effort to note readings, and there may be a possibility of human error. Such type of systems fails to provide and store precise values of parameters with high accuracy. Analog systems are having drawback of storage/memory. Therefore, there is a requirement of a smart system which is fully automated, accurate and capable enough to monitor all the environmental parameters with utmost possible accuracy. Besides, it should be cost-effective as well as portable too. This paper represents the Wireless Sensor (WS) data communication using DHT11, Arduino, SIM900A GSM module, a mobile device and Liquid Crystal Display (LCD). Experimental setup includes the heating arrangement of DHT11 and transmission of its data using Arduino and SIM900A GSM shield. The mobile device receives the data using Arduino, GSM shield and displays it on LCD too. Heating arrangement is used to heat and cool the temperature sensor to study its characteristics.

Keywords: wireless communication, Arduino, DHT11, LCD, SIM900A GSM module, mobile phone SMS

Procedia PDF Downloads 282

Authors: Aviv Yaniv, Ron Ben Arosh, Nadav Gasner, Michael Konviser, Arbel Yaniv

Abstract:

This paper introduces two methods for the evaluation of Question Decomposition Meaning Representation (QDMR) as predicted by sequence-to-sequence model and COPYNET parser for natural language questions processing, motivated by the fact that previous evaluation metrics used for this task do not take into account some characteristics of the representation, such as partial ordering structure. To this end, several heuristics to extract such partial dependencies are formulated, followed by the hereby proposed evaluation methods denoted as Proportional Graph Matcher (PGM) and Conversion to Normal String Representation (Nor-Str), designed to better capture the accuracy level of QDMR predictions. Experiments are conducted to demonstrate the efficacy of the proposed evaluation methods and show the added value suggested by one of them- the Nor-Str, for better distinguishing between high and low-quality QDMR when predicted by models such as COPYNET. This work represents an important step forward in the development of better evaluation methods for QDMR predictions, which will be critical for improving the accuracy and reliability of natural language question-answering systems.

Keywords: NLP, question answering, question decomposition meaning representation, QDMR evaluation metrics

Procedia PDF Downloads 78

Authors: Elham Serkani, Hossein Gharaee Garakani, Naser Mohammadzadeh, Elaheh Vaezpour

Abstract:

Intrusion detection systems (IDS) are the main components of network security. These systems analyze the network events for intrusion detection. The design of an IDS is through the training of normal traffic data or attack. The methods of machine learning are the best ways to design IDSs. In the method presented in this article, the pruning algorithm of C5.0 decision tree is being used to reduce the features of traffic data used and training IDS by the least square vector algorithm (LS-SVM). Then, the remaining features are arranged according to the predictor importance criterion. The least important features are eliminated in the order. The remaining features of this stage, which have created the highest level of accuracy in LS-SVM, are selected as the final features. The features obtained, compared to other similar articles which have examined the selected features in the least squared support vector machine model, are better in the accuracy, true positive rate, and false positive. The results are tested by the UNSW-NB15 dataset.

Keywords: decision tree, feature selection, intrusion detection system, support vector machine

Procedia PDF Downloads 265

Authors: Victoria Goodall, Paul Fatti, Norman Owen-Smith

Abstract:

Hidden Markov Models have become popular for the analysis of animal tracking data. These models are being used to model the movements of a variety of species in many areas around the world. A common assumption of the model is that the observations need to have regular time steps. In many ecological studies, this will not be the case. The objective of the research is to modify the movement model to allow for irregularly spaced locations and investigate the effect on the inferences which can be made about the latent states. A modification of the likelihood function to allow for these irregular spaced locations is investigated, without using interpolation or averaging the movement rate. The suitability of the modification is investigated using GPS tracking data for lion (Panthera leo) in South Africa, with many observations obtained during the night, and few observations during the day. Many nocturnal predator tracking studies are set up in this way, to obtain many locations at night when the animal is most active and is difficult to observe. Few observations are obtained during the day, when the animal is expected to rest and is potentially easier to observe. Modifying the likelihood function allows the popular Hidden Markov Model framework to be used to model these irregular spaced locations, making use of all the observed data.

Keywords: hidden Markov Models, irregular observations, animal movement modelling, nocturnal predator

Procedia PDF Downloads 244

Authors: Dong Wu, Michael Grenn

Abstract:

Managing software projects effectively is crucial for meeting deadlines, ensuring quality, and managing resources well. Traditional methods often struggle with predicting project timelines accurately due to uncertain schedules and complex data. This study addresses these challenges by combining time prediction algorithms with Large Language Models (LLMs). It makes use of real-world software project data to construct and validate a model. The model takes detailed project progress data such as task completion dynamic, team Interaction and development metrics as its input and outputs predictions of project timelines. To evaluate the effectiveness of this model, a comprehensive methodology is employed, involving simulations and practical applications in a variety of real-world software project scenarios. This multifaceted evaluation strategy is designed to validate the model's significant role in enhancing forecast accuracy and elevating overall management efficiency, particularly in complex software project environments. The results indicate that the integration of time prediction algorithms with LLMs has the potential to optimize software project progress management. These quantitative results suggest the effectiveness of the method in practical applications. In conclusion, this study demonstrates that integrating time prediction algorithms with LLMs can significantly improve the predictive accuracy and efficiency of software project management. This offers an advanced project management tool for the industry, with the potential to improve operational efficiency, optimize resource allocation, and ensure timely project completion.

Keywords: software project management, time prediction algorithms, large language models (LLMS), forecast accuracy, project progress prediction

Procedia PDF Downloads 79

Authors: Leah Ning

Abstract:

This paper discusses the development of a machine learning algorithm that accurately detects metastatic breast cancer (cancer has spread elsewhere from its origin part) in selected images that come from pathology scans of lymph node sections. Being able to develop an accurate artificial intelligence (AI) algorithm would help significantly in breast cancer diagnosis since manual examination of lymph node scans is both tedious and oftentimes highly subjective. The usage of AI in the diagnosis process provides a much more straightforward, reliable, and efficient method for medical professionals and would enable faster diagnosis and, therefore, more immediate treatment. The overall approach used was to train a convolution neural network (CNN) based on a set of pathology scan data and use the trained model to binarily classify if a new scan were benign or malignant, outputting a 0 or a 1, respectively. The final model’s prediction accuracy is very high, with 100% for the train set and over 70% for the test set. Being able to have such high accuracy using an AI model is monumental in regard to medical pathology and cancer detection. Having AI as a new tool capable of quick detection will significantly help medical professionals and patients suffering from cancer.

Keywords: breast cancer detection, AI, machine learning, algorithm

Procedia PDF Downloads 91

Authors: Kehabtimer Shiferaw Kotiso, Getachew Hailemariam, Abiy Seifu Estifanos

Abstract:

Introduction: Despite the highest share of low birth weight (LBW) for neonatal mortality and morbidity, predicting births with LBW for better intervention preparation is challenging. This study aims to predict LBW using a dataset encompassing 53,637 birth cohorts collected from 36 primary hospitals across seven regions in Ethiopia from February 2022 to June 2024. Methods: We identified ten explanatory variables related to maternal and neonatal characteristics, including maternal education, age, residence, history of miscarriage or abortion, history of preterm birth, type of pregnancy, number of livebirths, number of stillbirths, antenatal care frequency, and sex of the fetus to predict LBW. Using WEKA 3.8.2, we developed and compared seven machine learning algorithms. Data preprocessing included handling missing values, outlier detection, and ensuring data integrity in birth weight records. Model performance was evaluated through metrics such as accuracy, precision, recall, F1-score, and area under the Receiver Operating Characteristic curve (ROC AUC) using 10-fold cross-validation. Results: The results demonstrated that the decision tree, J48, logistic regression, and gradient boosted trees model achieved the highest accuracy (94.5% to 94.6%) with a precision of 93.1% to 93.3%, F1-score of 92.7% to 93.1%, and ROC AUC of 71.8% to 76.6%. Conclusion: This study demonstrates the effectiveness of machine learning models in predicting LBW. The high accuracy and recall rates achieved indicate that these models can serve as valuable tools for healthcare policymakers and providers in identifying at-risk newborns and implementing timely interventions to achieve the sustainable developmental goal (SDG) related to neonatal mortality.

Keywords: low birth weight, machine learning, classification, neonatal mortality, Ethiopia

Procedia PDF Downloads 21

Authors: Umar Albalawi, Sang C. Suh, Jinoh Kim

Abstract:

As internet continues to expand its usage with an enormous number of applications, cyber-threats have significantly increased accordingly. Thus, accurate detection of malicious traffic in a timely manner is a critical concern in today’s Internet for security. One approach for intrusion detection is to use Machine Learning (ML) techniques. Several methods based on ML algorithms have been introduced over the past years, but they are largely limited in terms of detection accuracy and/or time and space complexity to run. In this work, we present a novel method for intrusion detection that incorporates a set of supervised learning algorithms. The proposed technique provides high accuracy and outperforms existing techniques that simply utilizes a single learning method. In addition, our technique relies on partial flow information (rather than full information) for detection, and thus, it is light-weight and desirable for online operations with the property of early identification. With the mid-Atlantic CCDC intrusion dataset publicly available, we show that our proposed technique yields a high degree of detection rate over 99% with a very low false alarm rate (0.4%).

Keywords: intrusion detection, supervised learning, traffic classification, computer networks

Procedia PDF Downloads 350

Authors: Adewole A. Ayoade, Marshall R. Sweatt, John P. H. Steele, Qi Han, Khaled Al-Wahedi, Hamad Karki, William A. Yearsley

Abstract:

Understanding the behavioral characteristics of sensors is a crucial step in fusing data from several sensors of different types. This paper introduces a practical, real-time approach to integrate heterogeneous sensor data to achieve higher accuracy than would be possible from any one individual sensor in localizing a mobile robot. We use this approach in both indoor and outdoor environments and it is especially appropriate for those environments like oil and gas refineries due to their sparse and featureless nature. We have studied the individual contribution of each sensor data to the overall combined accuracy achieved from the fusion process. A Sequential Update Extended Kalman Filter(EKF) using validation gates was used to integrate GPS data, Compass data, WiFi data, Inertial Measurement Unit(IMU) data, Vehicle Velocity, and pose estimates from Fiducial marker system. Results show that the approach can enable a mobile robot to navigate autonomously in any environment using a priori information.

Keywords: inspection mobile robot, navigation, sensor fusion, sequential update extended Kalman filter

Procedia PDF Downloads 471

Authors: Pitimanus Bunlue

Abstract:

The objectives of this study were to identify the unique characteristics of Salaya Old market, Phutthamonthon, Nakhon Pathom and develop the effective video media to promote the homeland awareness among local people and the characteristic features of this community were collectively summarized based on historical data, community observation, and people’s interview. The acquired data were used to develop a media describing prominent features of the community. The quality of the media was later assessed by interviewing local people in the old market in terms of content accuracy, video, and narration qualities, and sense of homeland awareness after watching the video. The result shows a 6-minute video media containing historical data and outstanding features of this community was developed. Based on the interview, the content accuracy was good. The picture quality and the narration were very good. Most people developed a sense of homeland awareness after watching the video also as well.

Keywords: audio-visual, creating homeland awareness, Phutthamonthon Nakhon Pathom, research and development

Procedia PDF Downloads 291

Authors: Aishik Deb, Rituparna Sinha

Abstract:

We have developed an algorithm to detect the abnormal segment/"structural variation in the genome across a number of samples. We have worked on simulated as well as real data from the BAM Files and have designed a segmentation algorithm where abnormal segments are detected. This algorithm aims to improve the accuracy and performance of the existing CNV-CH algorithm. The next-generation sequencing (NGS) approach is very fast and can generate large sequences in a reasonable time. So the huge volume of sequence information gives rise to the need for Big Data and parallel approaches of segmentation. Therefore, we have designed a map-reduce approach for the existing CNV-CH algorithm where a large amount of sequence data can be segmented and structural variations in the human genome can be detected. We have compared the efficiency of the traditional and map-reduce algorithms with respect to precision, sensitivity, and F-Score. The advantages of using our algorithm are that it is fast and has better accuracy. This algorithm can be applied to detect structural variations within a genome, which in turn can be used to detect various genetic disorders such as cancer, etc. The defects may be caused by new mutations or changes to the DNA and generally result in abnormally high or low base coverage and quantification values.

Keywords: cancer detection, convex hull segmentation, map reduce, next generation sequencing

Procedia PDF Downloads 136

Authors: Asra Yousuf, Ajaykumar Tannirkulum

Abstract:

Inferring rural-urban migration trends can help design effective policies that promote better urban planning and rural development. In this paper, we describe how machine learning algorithms can be applied to predict internal migration decisions of people. We consider data collected from household surveys in Tamil Nadu to train our model. To measure the performance of the model, we use data on past migration from National Sample Survey Organisation of India. The factors for training the model include socioeconomic characteristic of each individual like age, gender, place of residence, outstanding loans, strength of the household, etc. and his past migration history. We perform a comparative analysis of the performance of a number of machine learning algorithm to determine their prediction accuracy. Our results show that machine learning algorithms provide a stronger prediction accuracy as compared to statistical models. Our goal through this research is to propose the use of data science techniques in understanding human decisions and behaviour in developing countries.

Keywords: development, migration, internal migration, machine learning, prediction

Procedia PDF Downloads 271

Authors: Qiang Zhang, Xiaojian Hu1

Abstract:

Intersection is the place where vehicles and pedestrians must pass through, turn and evacuate. Obtaining the motion data of vehicles near the intersection is of great significance for transportation research. Since there are usually many targets and there are more conflicts between targets, this makes it difficult to obtain vehicle motion parameters in traffic videos of intersections. According to the characteristics of traffic videos, this paper applies video technology to realize the automated track, count and trajectory extraction of vehicles to collect traffic data by roadside surveillance cameras installed near the intersections. Based on the video recognition method, the vehicles in each lane near the intersection are tracked with extracting trajectory and counted respectively in various degrees of occlusion and visibility. The performances are compared with current recognized CPU-based algorithms of real-time tracking-by-detection. The speed of the presented system is higher than the others and the system has a better real-time performance. The accuracy of direction has reached about 94.99% on average, and the accuracy of classification and statistics has reached about 75.12% on average.

Keywords: tracking and statistics, vehicle, signalized intersection, motion parameter, trajectory

Procedia PDF Downloads 221

Authors: Ana B. Vivas, Antonia Ypsilanti, Aristea I. Ladas, Angeles F. Estevez

Abstract:

Mild Cognitive Impairment (MCI) is considered an intermediate stage between normal and pathological aging, as a substantial percentage of people diagnosed with MCI converts later to dementia of the Alzheimer’s type. Memory is of the first cognitive processes to deteriorate in this condition. In the present study we employed the differential outcomes procedure (DOP) to improve visuospatial memory in a group of participants with MCI. The DOP requires the structure of a conditional discriminative learning task in which a correct choice response to a specific stimulus-stimulus association is reinforced with a particular reinforcer or outcome. A group of 10 participants with MCI, and a matched control group had to learn and keep in working memory four target locations out of eight possible locations where a shape could be presented. Results showed that participants with MCI had a statistically significant better terminal accuracy when a unique outcome was paired with a location (76% accuracy) as compared to a non differential outcome condition (64%). This finding suggests that the DOP is useful in improving working memory in MCI patients, which may delay their conversion to dementia.

Keywords: mild cognitive impairment, working memory, differential outcomes, cognitive process

Procedia PDF Downloads 460

Authors: Bin Ji, Kai Xu, Shunyu Yao, Jingjing Liu, Ye Pan

Abstract:

Human pose estimation is a popular research area in computer vision for its important application in human-machine interface. In recent years, 2D human pose estimation based on convolution neural network has got great progress and development. However, in more and more practical applications, people often need to deal with tasks based on video. It’s not far-fetched for us to consider how to combine the spatial and temporal information together to achieve a balance between computing cost and accuracy. To address this issue, this study proposes a new spatiotemporal model, namely Spatiotemporal Net (STNet) to combine both temporal and spatial information more rationally. As a result, the predicted keypoints heatmap is potentially more accurate and spatially more precise. Under the condition of ensuring the recognition accuracy, the algorithm deal with spatiotemporal series in a decoupled way, which greatly reduces the computation of the model, thus reducing the resource consumption. This study demonstrate the effectiveness of our network over the Penn Action Dataset, and the results indicate superior performance of our network over the existing methods.

Keywords: convolutional long short-term memory, deep learning, human pose estimation, spatiotemporal series

Procedia PDF Downloads 148

Authors: Nor Mazlin Zahari, Lian Gan, Xuerui Mao

Abstract:

The power production in wind farms and the mechanical loads on the turbines are strongly impacted by the wake of the wind turbine. Thus, there is a need for understanding and modelling the turbine wake dynamic in the wind farm and the layout optimization. Having a good wake model is important in predicting plant performance and understanding fatigue loads. In this paper, the Dynamic Mode Decomposition (DMD) was applied to the simulation data generated by a Direct Numerical Simulation (DNS) of flow around a turbine, perturbed by upstream inflow noise. This technique is useful in analyzing the wake flow, to predict its future states and to reflect flow dynamics associated with the coherent structures behind wind turbine wake flow. DMD was employed to describe the dynamic of the flow around turbine from the DNS data. Since the DNS data comes with the unstructured meshes and non-uniform grid, the interpolation of each occurring within each element in the data to obtain an evenly spaced mesh was performed before the DMD was applied. DMD analyses were able to tell us characteristics of the travelling waves behind the turbine, e.g. the dominant helical flow structures and the corresponding frequencies. As the result, the dominant frequency will be detected, and the associated spatial structure will be identified. The dynamic mode which represented the coherent structure will be presented.

Keywords: coherent structure, Direct Numerical Simulation (DNS), dominant frequency, Dynamic Mode Decomposition (DMD)

Procedia PDF Downloads 345

Authors: I. Gusti A. A. Rai Asmiwyati, Robert J. Corner, Ashraf M. Dewan

Abstract:

Change on land use/cover (LULC) dominantly affects spatial structure and function. It can have such impacts by disrupting social culture practice and disturbing physical elements. Thus, it has become essential to understand of the dynamics in time and space of LULC as it can be used as a critical input for developing sustainable LULC. This study was an attempt to map and monitor the LULC change in Bali Indonesia from 2003 to 2013. Using object based classification to improve the accuracy, and change detection, multi temporal land use/cover data were extracted from a set of ASTER satellite image. The overall accuracies of the classification maps of 2003 and 2013 were 86.99% and 80.36%, respectively. Built up area and paddy field were the dominant type of land use/cover in both years. Patch increase dominantly in 2003 illustrated the rapid paddy field fragmentation and the huge occurring transformation. This approach is new for the case of diverse urban features of Bali that has been growing fast and increased the classification accuracy than the manual pixel based classification.

Keywords: land use/cover, urban, Bali, ASTER

Procedia PDF Downloads 541

Authors: Kenneth Fon Mbah, Arash Habibi Lashkari, Ali A. Ghorbani

Abstract:

Phishing e-mails are a security issue that not only annoys online users, but has also resulted in significant financial losses for businesses. Phishing advertisements and pornographic e-mails are difficult to detect as attackers have been becoming increasingly intelligent and professional. Attackers track users and adjust their attacks based on users’ attractions and hot topics that can be extracted from community news and journals. This research focuses on deceptive Phishing attacks and their variants such as attacks through advertisements and pornographic e-mails. We propose a framework called Phishing Alerting System (PHAS) to accurately classify e-mails as Phishing, advertisements or as pornographic. PHAS has the ability to detect and alert users for all types of deceptive e-mails to help users in decision making. A well-known email dataset has been used for these experiments and based on previously extracted features, 93.11% detection accuracy is obtainable by using J48 and KNN machine learning techniques. Our proposed framework achieved approximately the same accuracy as the benchmark while using this dataset.

Keywords: phishing e-mail, phishing detection, anti phishing, alarm system, machine learning

Procedia PDF Downloads 340

Authors: Yu. I. Pigolkin, M. A. Garcia Corro

Abstract:

Age determination of unknown dead bodies in forensic personal identification is a complicated process which involves the application of numerous methods and techniques. Skeletal remains are less exposed to influences of environmental factors. In order to enhance the accuracy of forensic age estimation additional properties of bones correlating with age are required to be revealed. Material and Methods: Dimensional examination of the sella turcica was carried out on cadavers with the cranium opened by a circular vibrating saw. The sample consisted of a total of 90 Russian subjects, ranging in age from two months and 87 years. Results: The tendency of dimensional variations throughout life was detected. There were no observed gender differences in the morphometry of the sella turcica. The shared use of the sella turcica depth and length values revealed the possibility to categorize an examined sample in a certain age period. Conclusions: Based on the results of existing methods of age determination, the morphometry of the sella turcica can be an additional characteristic, amplifying the received values, and accordingly, increasing the accuracy of forensic biological age diagnosis.

Keywords: age–related changes in bone structures, forensic personal identification, sella turcica morphometry, body identification

Procedia PDF Downloads 275

Authors: Yenni Kurniawati

Abstract:

Students Prediction Skill in chemistry experiments is an important skill for pre-service chemistry students to stimulate students reflective thinking at each stage of many chemistry experiments, qualitatively and quantitatively. A Virtual Chemistry Laboratory was designed to give students opportunities and times to practicing many kinds of chemistry experiments repeatedly, everywhere and anytime, before they do a real experiment. The Virtual Chemistry Laboratory content was constructed using the Model of Educational Reconstruction and developed to enhance students ability to predicted the experiment results and analyzed the cause of error, calculating the accuracy and precision with carefully in using chemicals. This research showed students changing in making a decision and extremely beware with accuracy, but still had a low concern in precision. It enhancing students level of reflective thinking skill related to their prediction skill 1 until 2 stage in average. Most of them could predict the characteristics of the product in experiment, and even the result will going to be an error. In addition, they take experiments more seriously and curiously about the experiment results. This study recommends for a different subject matter to provide more opportunities for students to learn about other kinds of chemistry experiments design.

Keywords: virtual chemistry laboratory, chemistry experiments, prediction skill, pre-lab experiences

Procedia PDF Downloads 340

Authors: Mina Jafari, Kobra Hamraee, Saied Hossein Hosseini

Abstract:

The prediction of breast cancer disease is one of the challenges in medicine. In this paper we collected 528 records of women’s information who live in Kabul including demographic, life style, diet and pregnancy data. There are many classification algorithm in breast cancer prediction and tried to find the best model with most accurate result and lowest error rate. We evaluated some other common supervised algorithms in data mining to find the best model in prediction of breast cancer disease among afghan women living in Kabul regarding to momography result as target variable. For evaluating these algorithms we used Cross Validation which is an assured method for measuring the performance of models. After comparing error rate and accuracy of three models: Decision Tree, Naive Bays and Rule Induction, Decision Tree with accuracy of 94.06% and error rate of %15 is found the best model to predicting breast cancer disease based on the health care records.

Keywords: decision tree, breast cancer, probability, data mining

Procedia PDF Downloads 138

Authors: Erick C. Valverde, Wansu Lim

Abstract:

Facial emotion recognition (FER) system has been recently developed for more advanced computer vision applications. The ability to identify human emotions would enable smart healthcare facility to diagnose mental health illnesses (e.g., depression and stress) as well as better human social interactions with smart technologies. The FER system involves two steps: 1) face detection task and 2) facial emotion recognition task. It classifies the human expression in various categories such as angry, disgust, fear, happy, sad, surprise, and neutral. This system requires intensive research to address issues with human diversity, various unique human expressions, and variety of human facial features due to age differences. These issues generally affect the ability of the FER system to detect human emotions with high accuracy. Early stage of FER systems used simple supervised classification task algorithms like K-nearest neighbors (KNN) and artificial neural networks (ANN). These conventional FER systems have issues with low accuracy due to its inefficiency to extract significant features of several human emotions. To increase the accuracy of FER systems, deep learning (DL)-based methods, like convolutional neural networks (CNN), are proposed. These methods can find more complex features in the human face by means of the deeper connections within its architectures. However, the inference speed and computational costs of a DL-based FER system is often disregarded in exchange for higher accuracy results. To cope with this drawback, an optimized DL-based FER system is proposed in this study.An extreme version of Inception V3, known as Xception model, is leveraged by applying different network optimization methods. Specifically, network pruning and quantization are used to enable lower computational costs and reduce memory usage, respectively. To support low resource requirements, a 68-landmark face detector from Dlib is used in the early step of the FER system.Furthermore, a DL compiler is utilized to incorporate advanced optimization techniques to the Xception model to improve the inference speed of the FER system. In comparison to VGG-Net and ResNet50, the proposed optimized DL-based FER system experimentally demonstrates the objectives of the network optimization methods used. As a result, the proposed approach can be used to create an efficient and real-time FER system.

Keywords: deep learning, face detection, facial emotion recognition, network optimization methods

Procedia PDF Downloads 118

Authors: Abdullah Al Farwan, Ya Zhang

Abstract:

In today’s educational arena, it is critical to understand educational data and be able to evaluate important aspects, particularly data on student achievement. Educational Data Mining (EDM) is a research area that focusing on uncovering patterns and information in data from educational institutions. Teachers, if they are able to predict their students' class performance, can use this information to improve their teaching abilities. It has evolved into valuable knowledge that can be used for a wide range of objectives; for example, a strategic plan can be used to generate high-quality education. Based on previous data, this paper recommends employing data mining techniques to forecast students' final grades. In this study, five data mining methods, Decision Tree, JRip, Naive Bayes, Multi-layer Perceptron, and Random Forest with wrapper feature selection, were used on two datasets relating to Portuguese language and mathematics classes lessons. The results showed the effectiveness of using data mining learning methodologies in predicting student academic success. The classification accuracy achieved with selected algorithms lies in the range of 80-94%. Among all the selected classification algorithms, the lowest accuracy is achieved by the Multi-layer Perceptron algorithm, which is close to 70.45%, and the highest accuracy is achieved by the Random Forest algorithm, which is close to 94.10%. This proposed work can assist educational administrators to identify poor performing students at an early stage and perhaps implement motivational interventions to improve their academic success and prevent educational dropout.

Keywords: classification algorithms, decision tree, feature selection, multi-layer perceptron, Naïve Bayes, random forest, students’ academic performance

Procedia PDF Downloads 166

Authors: Mohammadreza Akbari, Pooya Soleimani Besheli, Reza Khalili, Davood Domiri Danji

Abstract:

In this conference, our aims are accuracy, capabilities and power at solving of the complicated non-linear partial differential. Our purpose is to enhance the ability to solve the mentioned nonlinear differential equations at basic science and engineering field and similar issues with a simple and innovative approach. As we know most of engineering system behavior in practical are nonlinear process (especially basic science and engineering field, etc.) and analytical solving (no numeric) these problems are difficult, complex, and sometimes impossible like (Fluids and Gas wave, these problems can't solve with numeric method, because of no have boundary condition) accordingly in this symposium we are going to exposure an innovative approach which we have named it Akbari-Ganji's Method or AGM in engineering, that can solve sets of coupled nonlinear differential equations (ODE, PDE) with high accuracy and simple solution and so this issue will emerge after comparing the achieved solutions by Numerical method (Runge-Kutta 4th). Eventually, AGM method will be proved that could be created huge evolution for researchers, professors and students in whole over the world, because of AGM coding system, so by using this software we can analytically solve all complicated linear and nonlinear partial differential equations, with help of that there is no difficulty for solving all nonlinear differential equations. Advantages and ability of this method (AGM) as follow: (a) Non-linear Differential equations (ODE, PDE) are directly solvable by this method. (b) In this method (AGM), most of the time, without any dimensionless procedure, we can solve equation(s) by any boundary or initial condition number. (c) AGM method always is convergent in boundary or initial condition. (d) Parameters of exponential, Trigonometric and Logarithmic of the existent in the non-linear differential equation with AGM method no needs Taylor expand which are caused high solve precision. (e) AGM method is very flexible in the coding system, and can solve easily varieties of the non-linear differential equation at high acceptable accuracy. (f) One of the important advantages of this method is analytical solving with high accuracy such as partial differential equation in vibration in solids, waves in water and gas, with minimum initial and boundary condition capable to solve problem. (g) It is very important to present a general and simple approach for solving most problems of the differential equations with high non-linearity in engineering sciences especially at civil engineering, and compare output with numerical method (Runge-Kutta 4th) and Exact solutions.

Keywords: new approach, AGM, sets of coupled nonlinear differential equation, exact solutions, numerical

Procedia PDF Downloads 463

Authors: Pamela Ventola, Laurel Bales, Sara Florczyk

Abstract:

Background: Fully remote or hybrid administration of clinical outcome measures in rare neurodevelopmental disorders trials is increasing due to the ongoing pandemic and recognition that remote assessments reduce the burden on families. Many assessments in rare neurodevelopmental disorders trials are complex; however, remote/hybrid trials readily allow for the use of centralized raters to administer and score the scales. The use of centralized raters has many benefits, including reducing site burden; however, a specific impact on data quality has not yet been determined. Purpose: The current study has two aims: a) evaluate differences in data quality between administration of a standardized clinical interview completed by centralized raters compared to those completed by site raters and b) evaluate improvement in accuracy of scoring standardized developmental assessments when scored centrally compared to when scored by site raters. Methods: For aim 1, the Vineland-3, a widely used measure of adaptive functioning, was administered by site raters (n= 52) participating in one of four rare disease trials. The measure was also administered as part of two additional trials that utilized central raters (n=7). Each rater completed a comprehensive training program on the assessment. Following completion of the training, each clinician completed a Vineland-3 with a mock caregiver. Administrations were recorded and reviewed by a neuropsychologist for administration and scoring accuracy. Raters were able to certify for the trials after demonstrating an accurate administration of the scale. For site raters, 25% of each rater’s in-study administrations were reviewed by a neuropsychologist for accuracy of administration and scoring. For central raters, the first two administrations and every 10th administration were reviewed. Aim 2 evaluated the added benefit of centralized scoring on the accuracy of scoring of the Bayley-3, a comprehensive developmental assessment widely used in rare neurodevelopmental disorders trials. Bayley-3 administrations across four rare disease trials were centrally scored. For all administrations, the site rater who administered the Bayley-3 scored the scale, and a centralized rater reviewed the video recordings of the administrations and also scored the scales to confirm accuracy. Results: For aim 1, site raters completed 138 Vineland-3 administrations. Of the138 administrations, 53 administrations were reviewed by a neuropsychologist. Four of the administrations had errors that compromised the validity of the assessment. The central raters completed 180 Vineland-3 administrations, 38 administrations were reviewed, and none had significant errors. For aim 2, 68 administrations of the Bayley-3 were reviewed and scored by both a site rater and a centralized rater. Of these administrations, 25 had errors in scoring that were corrected by the central rater. Conclusion: In rare neurodevelopmental disorders trials, sample sizes are often small, so data quality is critical. The use of central raters inherently decreases site burden, but it also decreases rater variance, as illustrated by the small team of central raters (n=7) needed to conduct all of the assessments (n=180) in these trials compared to the number of site raters (n=53) required for even fewer assessments (n=138). In addition, the use of central raters dramatically improves the quality of scoring the assessments.

Keywords: neurodevelopmental disorders, clinical trials, rare disease, central raters, remote trials, decentralized trials

Procedia PDF Downloads 172

Authors: Hui-Ling Huang, Tamara Vasylenko, Phasit Charoenkwan, Shih-Hsiang Chiu, Shinn-Ying Ho

Abstract:

The knowledge of the human transporters is still limited due to technically demanding procedure of crystallization for the structural characterization of transporters by spectroscopic methods. It is desirable to develop bioinformatics tools for effective analysis of available sequences in order to identify human transmembrane transporter proteins (HMTPs). This study proposes a scoring card method (SCM) based method for predicting HMTPs. We estimated a set of propensity scores of dipeptides to be HMTPs using SCM from the training dataset (HTS732) consisting of 366 HMTPs and 366 non-HMTPs. SCM using the estimated propensity scores of 20 amino acids and 400 dipeptides -as HMTPs, has a training accuracy of 87.63% and a test accuracy of 66.46%. The five top-ranked dipeptides include LD, NV, LI, KY, and MN with scores 996, 992, 989, 987, and 985, respectively. Five amino acids with the highest propensity scores are Ile, Phe, Met, Gly, and Leu, that hydrophobic residues are mostly highly-scored. Furthermore, obtained propensity scores were used to analyze physicochemical properties of human transporters.

Keywords: dipeptide composition, physicochemical property, human transmembrane transporter proteins, human transmembrane transporters binding propensity, scoring card method

Procedia PDF Downloads 369

Authors: Thota Sai Prakash, B. Yaswanth, Jhade Bhuvaneswar, Marreddy Divakar Reddy, Shyam Ji Gupta

Abstract:

Across the globe, there are a lot of chronic diseases, and heart disease stands out as one of the most perilous. Sadly, many lives are lost to this condition, even though early intervention could prevent such tragedies. However, identifying heart disease in its initial stages is not easy. To address this challenge, we propose an automated system aimed at predicting the presence of heart disease using advanced techniques. By doing so, we hope to empower individuals with the knowledge needed to take proactive measures against this potentially fatal illness. Our approach towards this problem involves meticulous data preprocessing and the development of predictive models utilizing classification algorithms such as Support Vector Machines (SVM), Decision Tree, and Random Forest. We assess the efficiency of every model based on metrics like accuracy, ensuring that we select the most reliable option. Additionally, we conduct thorough data analysis to reveal the importance of different attributes. Among the models considered, Random Forest emerges as the standout performer with an accuracy rate of 96.04% in our study.

Keywords: support vector machines, decision tree, random forest

Procedia PDF Downloads 40

Authors: Vahid Bayrami Rad

Abstract:

In recent years, the use of artificial intelligence techniques, tools, and methods in processing medical images and health-related applications has been highlighted and a lot of research has been done in this regard. For example, colonoscopy and diagnosis of colon lesions are some cases in which the process of diagnosis of lesions can be improved by using image processing and artificial intelligence algorithms, which help doctors a lot. Due to the lack of accurate measurements and the variety of injuries in colonoscopy images, the process of diagnosing the type of lesions is a little difficult even for expert doctors. Therefore, by using different software and image processing, doctors can be helped to increase the accuracy of their observations and ultimately improve their diagnosis. Also, by using automatic methods, the process of diagnosing the type of disease can be improved. Therefore, in this paper, a deep learning framework called KCBA is proposed to classify colonoscopy lesions which are composed of several methods such as K-means clustering, a bag of features and deep auto-encoder. Finally, according to the experimental results, the proposed method's performance in classifying colonoscopy images is depicted considering the accuracy criterion.

Keywords: colorectal cancer, colonoscopy, region of interest, narrow band imaging, texture analysis, bag of feature

Procedia PDF Downloads 57

Authors: Samar M. Alqhtani, Suhuai Luo, Brian Regan

Abstract:

Data fusion technology can be the best way to extract useful information from multiple sources of data. It has been widely applied in various applications. This paper presents a data fusion approach in multimedia data for event detection in twitter by using Dempster-Shafer evidence theory. The methodology applies a mining algorithm to detect the event. There are two types of data in the fusion. The first is features extracted from text by using the bag-ofwords method which is calculated using the term frequency-inverse document frequency (TF-IDF). The second is the visual features extracted by applying scale-invariant feature transform (SIFT). The Dempster - Shafer theory of evidence is applied in order to fuse the information from these two sources. Our experiments have indicated that comparing to the approaches using individual data source, the proposed data fusion approach can increase the prediction accuracy for event detection. The experimental result showed that the proposed method achieved a high accuracy of 0.97, comparing with 0.93 with texts only, and 0.86 with images only.

Keywords: data fusion, Dempster-Shafer theory, data mining, event detection

Procedia PDF Downloads 410